School of Health Science and Engineering, University of Shanghai for Science and Technology, Shanghai, China.
Department of Radiology, Changhai Hospital, The Navy Military Medical University, Shanghai, China.
J Appl Clin Med Phys. 2023 Dec;24(12):e14204. doi: 10.1002/acm2.14204. Epub 2023 Nov 8.
The segmentation and recognition of pancreatic tumors are crucial tasks in the diagnosis and treatment of pancreatic diseases. However, due to the relatively small proportion of the pancreas in the abdomen and significant shape and size variations, pancreatic tumor segmentation poses considerable challenges.
To construct a network model that combines a pyramid pooling module with Inception architecture and SE attention mechanism (PIS-Unet), and observe its effectiveness in pancreatic tumor images segmentation, thereby providing supportive recommendations for clinical practitioners.
A total of 303 patients with histologically confirmed pancreatic cystic neoplasm (PCN), including serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN), from Shanghai Changhai Hospital between March 2011 and November 2021 were included. A total of 1792 T2-weighted imaging (T2WI) slices were used to build a CNN model. The model employed a pyramid pooling Inception module with a fused attention mechanism. The attention mechanism enhanced the network's focus on local features, while the Inception module and pyramid pooling allowed the network to extract features at different scales and improve the utilization efficiency of global information, thereby effectively enhancing network performance.
Using three-fold cross-validation, the model constructed by us achieved a dice score of 85.49 ± 2.02 for SCN images segmentation, and a dice score of 87.90 ± 4.19 for MCN images segmentation.
This study demonstrates that using deep learning networks for the segmentation of PCNs yields favorable results. Applying this network as an aid to physicians in PCN diagnosis shows potential for clinical applications.
胰腺肿瘤的分割和识别是胰腺疾病诊断和治疗的关键任务。然而，由于胰腺在腹部的比例相对较小，并且形状和大小变化很大，胰腺肿瘤的分割具有相当大的挑战性。
构建一种结合金字塔池化模块、Inception 架构和 SE 注意力机制的网络模型（PIS-Unet），观察其在胰腺肿瘤图像分割中的有效性，从而为临床医生提供支持性建议。
纳入 2011 年 3 月至 2021 年 11 月期间上海长海医院经组织学证实的胰腺囊性肿瘤（PCN）患者 303 例，包括浆液性囊腺瘤（SCN）和黏液性囊腺瘤（MCN）。共使用 1792 张 T2 加权成像（T2WI）切片构建 CNN 模型。该模型采用具有融合注意力机制的金字塔池化 Inception 模块。注意力机制增强了网络对局部特征的关注，而 Inception 模块和金字塔池化允许网络在不同尺度上提取特征，提高全局信息的利用效率，从而有效增强网络性能。
使用三折交叉验证，我们构建的模型对 SCN 图像分割的 Dice 得分为 85.49±2.02，对 MCN 图像分割的 Dice 得分为 87.90±4.19。
本研究表明，使用深度学习网络进行 PCN 分割可取得良好效果。将该网络作为 PCN 诊断的辅助工具，具有潜在的临床应用价值。
